Raw data from chambers is received. Based on received raw data, if a fault exists in operations of the chambers is detected. The detecting includes at least one of operations outlined below. Sigma values respectively corresponding to the chambers are generated based on the raw data of the chambers. A determination is made to determine whether a sigma ratio corresponding to the sigma values is smaller than a threshold value. Mean outlier indexes respectively corresponding to the chambers is generated by executing a mean matching process for the chambers in a condition that the sigma ratio is smaller than the threshold value. One of the chambers, which has a worst first mean outlier index of the first mean outlier indexes, is identified as a target chamber having fault operation.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method comprising: receiving raw data from a plurality of chambers; based on received raw data of the plurality of chambers, detecting if a fault exists in operations of the plurality of chambers, wherein the detecting comprises at least one of: based on the received raw data of the plurality of chambers, generating a plurality of first sigma values corresponding to the plurality of chambers; in a condition that a sigma ratio corresponding to the plurality of first sigma values is smaller than a threshold value, generating a plurality of first mean outlier indexes corresponding to the plurality of chambers by executing a mean matching process for the plurality of chambers; and identifying that one of the plurality of chambers, which has a worst first mean outlier index of the plurality of first mean outlier indexes, is a target chamber having fault operation; and sending, from a host device to the target chamber, updated configuration data based on the detected fault to modify the fault operation of the target chamber.
2. The method of claim 1 , wherein generating the plurality of first sigma values comprises: calculating a standard deviation for the raw data of the plurality of chambers.
3. The method of claim 1 , wherein the sigma ratio is a ratio of a square of a largest sigma value to a square of a smallest sigma value among the plurality of first sigma values.
4. The method of claim 1 , wherein the mean matching process comprises: calculating a mean value for the raw data of each one of the plurality of chambers; and comparing each mean value of the plurality of chambers with the other mean values, to generate the plurality of first mean outlier indexes corresponding to the plurality of chambers.
5. The method of claim 1 , wherein the detecting further comprises at least one of: in a condition that the sigma ratio is larger than or equal to the threshold value, executing a noise-filtering process for the raw data of the plurality of chambers; after the noise-filtering process is executed, generating a plurality of sigma outlier indexes corresponding to the plurality of chambers by executing a sigma matching process for the plurality of chambers; after the noise-filtering process is executed, generating a plurality of second mean outlier indexes corresponding to the plurality of chambers by executing the mean matching process for the plurality of chambers; and identifying that one of the plurality of chambers, which has a worst sum of the plurality of sigma outlier indexes and the plurality of second mean outlier indexes, is the target chamber.
6. The method of claim 5 , wherein the noise-filtering process comprises: determining that the raw data, larger than a boundary value, of each one of the plurality of chambers is noise; and filtering the noise from the raw data of each one of the plurality of chambers.
7. The method of claim 5 , wherein the sigma matching process comprises: calculating a standard deviation for the raw data of the plurality of chambers to generate a plurality of second sigma values corresponding to the plurality of chambers; and comparing each one of the plurality of second sigma values with the others of the plurality of second sigma values, to generate the plurality of sigma outlier indexes corresponding to the plurality of chambers.
8. The method of claim 5 , wherein the mean matching process comprises: calculating a mean value for the raw data of each one of the plurality of chambers; and comparing each mean value of the plurality of chambers with the other mean values, to generate the plurality of second mean outlier indexes corresponding to the plurality of chambers.
9. A method comprising: based on raw data received from a first chamber and a second chamber, detecting if a fault exists in operations of the first chamber and the second chamber, wherein the detecting comprises at least one of: configuring the first chamber to become a plurality of virtual chambers, wherein each one of the plurality of virtual chambers comprises a part of the raw data of the first chamber; based on the raw data of the first chamber and the second chamber, generating a first sigma value and a second sigma value respectively corresponding to the first chamber and the second chamber; in a condition that a sigma ratio corresponding to the first sigma value and the second sigma value is smaller than a threshold value, generating a plurality of first mean outlier indexes respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers by executing a mean matching process for the first chamber, the second chamber and the plurality of virtual chambers; and identifying that the first chamber is a target chamber having fault operation, when one of the plurality of virtual chambers and the first chamber has a worst first mean outlier index of the plurality of first mean outlier indexes among the first chamber, the second chamber and the plurality of virtual chambers; and sending, from a host device to the target chamber, updated configuration data based on the detected fault to modify the fault operation of the target chamber.
10. The method of claim 9 , wherein generating the first sigma value and the second sigma value comprises: calculating a standard deviation for the raw data of the first chamber and the second chamber, to generate the first sigma value and the second sigma value.
11. The method of claim 9 , wherein the sigma ratio is a ratio of a square of a largest sigma value to a square of a smallest sigma value among the first sigma value and the second sigma value.
12. The method of claim 9 , wherein the mean matching process comprises: calculating a mean value for the raw data of each one of the first chamber, the second chamber and the plurality of virtual chambers; and comparing each mean value of the first chamber, the second chamber and the plurality of virtual chambers with the other mean values, to generate the plurality of first mean outlier indexes respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers.
13. The method of claim 9 , wherein the detecting further comprises at least one of: in a condition that the sigma ratio is larger than or equal to the threshold value, executing a noise-filtering process for the raw data of each one of the first chamber, the second chamber and the plurality of virtual chambers; after the noise-filtering process is executed, generating a plurality of sigma outlier indexes respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers by executing a sigma matching process for the first chamber, the second chamber and the plurality of virtual chambers; after the noise-filtering process is executed, generating a plurality of second mean outlier indexes respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers by executing the mean matching process for the first chamber, the second chamber and the plurality of virtual chambers; and identifying that the first chamber is the target chamber when one of the plurality of virtual chambers and the first chamber has a worst sum of the plurality of sigma outlier indexes and the plurality of second mean outlier indexes among the first chamber, the second chamber and the plurality of virtual chambers, and identifying that the second chamber is the target chamber when the second chamber has the worst sum of the plurality of sigma outlier indexes and the plurality of second mean outlier indexes among the first chamber, the second chamber and the plurality of virtual chambers.
14. The method of claim 13 , wherein the noise-filtering process comprises: determining that the raw data, larger than a boundary value, of each one of the first chamber, the second chamber and the plurality of virtual chambers is noise; and filtering the noise from the raw data of each one of the first chamber, the second chamber and the plurality of virtual chambers.
15. The method of claim 13 , wherein the sigma matching process comprises: calculating a standard deviation for the raw data of each one of the first chamber, the second chamber and the plurality of virtual chambers, to generate a plurality of third sigma values respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers; and comparing each one of the plurality of third sigma values with the other plurality of third sigma values, to generate the plurality of sigma outlier indexes respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers.
16. The method of claim 13 , wherein the mean matching process comprises: calculating a mean value for the raw data of each one of the first chamber, the second chamber and the plurality of virtual chambers; and comparing each mean value of the first chamber, the second chamber and the plurality of virtual chambers with the other mean values, to generate the plurality of second mean outlier indexes respectively corresponding to the first chamber, the second chamber and the plurality of virtual chambers.
17. A system comprising: a plurality of chambers; and a host device configured: to receive raw data from the plurality of chambers, and based on received raw data, to detect if a target fault chamber exists in the plurality of chambers by at least one of: generating a plurality of first sigma values corresponding to the plurality of chambers; based on a sigma ratio corresponding to the plurality of first sigma values, generating a plurality of first mean outlier indexes corresponding to the plurality of chambers; and based on the plurality of first mean outlier indexes, identifying a target chamber having fault operation as the target fault chamber; and if the target fault chamber exists, to modify the fault operation of the target chamber by sending updated configuration data to the target fault chamber.
18. The system of claim 17 , wherein the sigma ratio is a ratio of a square of a largest first sigma value to a square of a smallest first sigma value among the plurality of first sigma values.
19. The system of claim 17 , wherein in a condition that the sigma ratio is larger than or equal to a threshold value, the host device is configured to execute a noise-filtering process for the raw data of the plurality of chambers.
20. The system of claim 19 , wherein the host device is configured to detect if a target fault chamber exists in the plurality of chambers further by at least one of: after the noise-filtering process is executed, generating a plurality of sigma outlier indexes corresponding to the plurality of chambers; based on second mean values corresponding to the raw data, generating a plurality of second mean outlier indexes corresponding to the plurality of chambers; and based on the plurality of sigma outlier indexes and the plurality of second mean outlier indexes, identifying a target chamber having fault operation as the target fault chamber.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 12, 2016
November 13, 2018
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.